Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55384
    Prev
    Next
    INDEX
    Explanations

    logging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     सिल
    -0.08
     cement
    -0.07
     stake
    -0.07
     annih
    -0.07
     repairing
    -0.07
    クリック
    -0.07
     EPC
    -0.07
     glitch
    -0.07
    }px
    -0.07
     olduğu
    -0.07
    POSITIVE LOGITS
    =logging
    0.10
     설정
    0.09
    Configured
    0.09
     configured
    0.09
    Configure
    0.09
     Configure
    0.08
     настрой
    0.08
    .level
    0.08
    _initialized
    0.08
     настро
    0.08
    Activations Density 0.003%

    No Known Activations